KAUST Grant NumberOSR-2015-CRG4-2639
Permanent link to this recordhttp://hdl.handle.net/10754/626708
MetadataShow full item record
AbstractWe study the problem of detecting human-object interactions (HOI) in static images, defined as predicting a human and an object bounding box with an interaction class label that connects them. HOI detection is a fundamental problem in computer vision as it provides semantic information about the interactions among the detected objects. We introduce HICO-DET, a new large benchmark for HOI detection, by augmenting the current HICO classification benchmark with instance annotations. To solve the task, we propose Human-Object Region-based Convolutional Neural Networks (HO-RCNN). At the core of our HO-RCNN is the Interaction Pattern, a novel DNN input that characterizes the spatial relations between two bounding boxes. Experiments on HICO-DET demonstrate that our HO-RCNN, by exploiting human-object spatial relations through Interaction Patterns, significantly improves the performance of HOI detection over baseline approaches.
CitationChao, Y.-W., Liu, Y., Liu, X., Zeng, H., & Deng, J. (2018). Learning to Detect Human-Object Interactions. 2018 IEEE Winter Conference on Applications of Computer Vision (WACV). doi:10.1109/wacv.2018.00048
SponsorsThis publication is based upon work supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No. OSR-2015-CRG4-2639.
Conference/Event name18th IEEE Winter Conference on Applications of Computer Vision, WACV 2018